Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1593 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.6521. Min Range: -1.6521

Max Act: 1.6521. Min Act: -0.0000

Data Index: 1348991 (C4 (Web Text))

Max Activating Token Index: 245

Text #1

Max Range: 1.6521. Min Range: -1.6521

Max Act: 1.3408. Min Act: -0.0000

Data Index: 470519 (C4 (Web Text))

Max Activating Token Index: 740

Text #2

Max Range: 1.6521. Min Range: -1.6521

Max Act: 1.0996. Min Act: -0.0000

Data Index: 838077 (C4 (Web Text))

Max Activating Token Index: 291

Text #3

Max Range: 1.6521. Min Range: -1.6521

Max Act: 1.2177. Min Act: -0.0000

Data Index: 428707 (C4 (Web Text))

Max Activating Token Index: 118

Text #4

Max Range: 1.6521. Min Range: -1.6521

Max Act: 1.2764. Min Act: -0.0000

Data Index: 1029681 (C4 (Web Text))

Max Activating Token Index: 146

Text #5

Max Range: 1.6521. Min Range: -1.6521

Max Act: 0.9916. Min Act: -0.0000

Data Index: 247955 (C4 (Web Text))

Max Activating Token Index: 375

Text #6

Max Range: 1.6521. Min Range: -1.6521

Max Act: 1.0878. Min Act: -0.0000

Data Index: 648953 (C4 (Web Text))

Max Activating Token Index: 805

Text #7

Max Range: 1.6521. Min Range: -1.6521

Max Act: 0.7997. Min Act: -0.0000

Data Index: 325195 (C4 (Web Text))

Max Activating Token Index: 995

Text #8

Max Range: 1.6521. Min Range: -1.6521

Max Act: 0.7571. Min Act: -0.0000

Data Index: 1063626 (C4 (Web Text))

Max Activating Token Index: 479

Text #9

Max Range: 1.6521. Min Range: -1.6521

Max Act: 0.7299. Min Act: -0.0000

Data Index: 511586 (C4 (Web Text))

Max Activating Token Index: 657

Text #10

Max Range: 1.6521. Min Range: -1.6521

Max Act: 0.7215. Min Act: -0.0000

Data Index: 464636 (C4 (Web Text))

Max Activating Token Index: 740

Text #11

Max Range: 1.6521. Min Range: -1.6521

Max Act: 0.6601. Min Act: -0.0000

Data Index: 907312 (C4 (Web Text))

Max Activating Token Index: 474

Text #12

Max Range: 1.6521. Min Range: -1.6521

Max Act: 0.6686. Min Act: -0.0000

Data Index: 1053653 (C4 (Web Text))

Max Activating Token Index: 727

Text #13

Max Range: 1.6521. Min Range: -1.6521

Max Act: 0.7082. Min Act: -0.0000

Data Index: 759033 (C4 (Web Text))

Max Activating Token Index: 567

Text #14

Max Range: 1.6521. Min Range: -1.6521

Max Act: 0.6319. Min Act: -0.0000

Data Index: 854865 (C4 (Web Text))

Max Activating Token Index: 443

Text #15

Max Range: 1.6521. Min Range: -1.6521

Max Act: 0.8121. Min Act: -0.0000

Data Index: 302487 (C4 (Web Text))

Max Activating Token Index: 660

Text #16

Max Range: 1.6521. Min Range: -1.6521

Max Act: 0.6817. Min Act: -0.0000

Data Index: 1051563 (C4 (Web Text))

Max Activating Token Index: 709

Text #17

Max Range: 1.6521. Min Range: -1.6521

Max Act: 0.6505. Min Act: -0.0000

Data Index: 585974 (C4 (Web Text))

Max Activating Token Index: 605

Text #18

Max Range: 1.6521. Min Range: -1.6521

Max Act: 0.6642. Min Act: -0.0000

Data Index: 85622 (C4 (Web Text))

Max Activating Token Index: 613

Text #19

Max Range: 1.6521. Min Range: -1.6521

Max Act: 0.6013. Min Act: -0.0000

Data Index: 1198985 (C4 (Web Text))

Max Activating Token Index: 189